Search and retrieve articles from the Sovereign AI Blog. A practical engineering log of self-hosted AI on NVIDIA DGX Spark with articles covering SGLang, Mistral, Voxtral, OpenClaw. Tools: search_blog, get_article, diagnose_sglang.
Endpoint URL: https://mcp.sovgrid.org/self-hosted-ai?ref=smithery
Transport: streamable-http (oder „HTTP Streaming")
Tags/Categories: knowledge-base, search, self-hosted-ai, sovereign
Validate an SGLang configuration for NVIDIA DGX Spark (GB10/SM121A).
Pure pattern-matching against known failure modes documented in the Sovereign AI Blog. No inference, no external calls. Returns critical issues, non-fatal warnings, and a recommended baseline config.
All parameters are optional; supply only what you have. With no inputs you get the recommended config and a 'unknown' verdict.
| Name | Required | Description | Default |
|---|---|---|---|
| hardware | No | Hardware description (e.g. 'GB10', 'DGX Spark', 'SM121A'). Empty = skip GB10-specific rules. | |
| image_tag | No | Docker image tag in use (e.g. 'lmsysorg/sglang:latest', 'lmsysorg/sglang:v0.4.0'). Empty = skip. | |
| mem_fraction | No | SGLang --mem-fraction-static value (e.g. 0.88). 0.0 = skip this check. | |
| error_message | No | Paste error log output here for pattern matching against known failure modes. | |
| attention_backend | No | SGLang --attention-backend value (e.g. 'flashinfer', 'triton'). Empty string = skip this check. | |
| cuda_graph_max_bs | No | SGLang --cuda-graph-max-bs value. 0 = skip this check. |
| Name | Required | Description |
|---|---|---|
| issues | Yes | Critical issues that will prevent SGLang from running correctly |
| verdict | Yes | Overall verdict. 'unknown' = no inputs provided. |
| warnings | Yes | Non-fatal warnings (suboptimal but non-blocking) |
| recommended_config | Yes | Verified-good baseline config for GB10/SM121A |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only and idempotent hints. The description adds valuable behavioral context: it explicitly states the tool does pure pattern-matching, makes no external calls, and returns issues, warnings, and a recommended config, including the no-input edge case.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is compact and well-structured: it states the core purpose, explains the method, describes outputs, and covers the all-optional edge case. Every sentence contributes meaningful information without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With a full output schema and detailed parameter descriptions, the description appropriately covers the tool's scope, behavior, and edge cases. It is sufficient for an agent to understand when and how to invoke the tool, including the no-input scenario.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema covers all parameters with detailed descriptions and skip semantics. The description adds only the general note that all parameters are optional, which is helpful but not a substantial enhancement over the schema's existing parameter-level guidance.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool validates an SGLang configuration for NVIDIA DGX Spark, specifying the exact verb and resource. It distinguishes itself from sibling content-retrieval tools by outlining its diagnostic pattern-matching purpose and return types.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives clear context for when to use the tool (validate SGLang config) and notes that all parameters are optional, implying you supply what you have. It does not explicitly list exclusions or alternative tools, but the distinct purpose makes it unambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve the full content of a blog article by its slug.
Returns the article body (Markdown) plus metadata. If the slug does not
match any article, returns an Article with `error='article_not_found'`
and other fields at their defaults.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | Article slug as returned by search_blog (e.g. 'setup-llm-inference-setup'). Lower-case, hyphenated. |
| Name | Required | Description |
|---|---|---|
| url | No | Public URL of the article |
| body | No | Full article body in Markdown |
| date | No | Publication date (ISO 8601) |
| slug | Yes | Article slug |
| tags | No | Topic tags assigned to the article |
| error | No | Set to 'article_not_found' if no article matches the slug |
| title | No | Article title |
| word_count | No | Word count of the article body |
| description | No | Short article description |
| quality_class | No | Editorial content class (e.g. 'Ephemeral', 'Evergreen'). Empty if not classified. |
| quality_score | No | Build-time quality score from the editorial pipeline (unbounded weighted composite across 13 signals, higher is better; thresholds depend on style) |
| quality_style | No | Editorial style category (e.g. 'best_practice_learnings', 'werthaltige_code_beispiele'). Empty if not categorised. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds valuable behavioral context beyond the annotations: it specifies the return format (Markdown body plus metadata) and the exact error behavior when the slug is not found. This is particularly helpful for an agent to handle failure cases gracefully.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the action, and every sentence adds value. It avoids redundancy and is easy to parse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple retrieval tool with one parameter, the description covers the core function, return value, and error case. The output schema provides additional structural details, so the description is complete and well-suited for the tool's complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides a rich description of the slug parameter, including an example and format guidance (lower-case, hyphenated). The description itself adds no new semantics about the parameter, so the baseline of 3 applies since schema coverage is 100%.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves the full content of a blog article by slug, which distinguishes it from sibling tools like search_blog that likely list or search articles. The verb 'Retrieve' and resource 'blog article' are specific, leaving no ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when you have a slug ('by its slug'), but it does not explicitly mention alternatives or when to use this tool versus search_blog or list_tags. The parameter schema references search_blog, but that is outside the description itself, so guidance is implied rather than explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all topic tags used across the Sovereign AI Blog corpus, with article
counts. Use this to browse the topic space before calling search_blog with
a tag filter.
| Name | Required | Description | Default |
|---|---|---|---|
| sort | No | Result ordering. 'count_desc' lists most-used tags first (default). 'alpha' sorts alphabetically. | count_desc |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and idempotentHint, covering the safety profile. The description adds behavioral context by noting the tool returns article counts and lists 'all' tags, which is useful beyond the annotations. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, directly states the purpose and usage context without any fluff. Every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (one optional param, output schema provided), the description sufficiently covers what the tool does, what it returns (tags with counts), and when to use it. No critical information is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema fully documents the only parameter 'sort' with its enum and description, so the baseline is 3. The tool description does not add extra parameter semantics, but none are needed given the schema coverage is 100%.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool lists all topic tags with article counts, using a specific verb 'List' and a specific resource ('topic tags'). It distinguishes itself from siblings by explicitly mentioning browsing the topic space before using search_blog with a tag filter.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit usage guidance: 'Use this to browse the topic space before calling search_blog with a tag filter.' This tells the agent when to use this tool and names the alternative tool, making the decision clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the Sovereign AI Blog for articles matching a natural language query,
optionally filtered by tag and sorted by relevance or date.
Behaviour matrix:
- query='', sort=* -> list newest-first, optionally tag-filtered
- query!='', sort=relevance -> TF-IDF ranked, optionally tag-filtered
- query!='', sort=date_desc -> TF-IDF filtered (score > 0.001), then sorted by date
Pure read-only, deterministic for a given KB snapshot.
| Name | Required | Description | Default |
|---|---|---|---|
| n | No | Maximum number of results to return | |
| tag | No | Optional tag filter (e.g. 'setup', 'fixes', 'strategy'). Only articles with this tag are considered. Use list_tags to discover available tags. | |
| sort | No | Result ordering. 'relevance' uses TF-IDF score (default for non-empty query). 'date_desc' sorts newest first (default behaviour when query is empty). When query is empty, 'relevance' is treated as 'date_desc'. | relevance |
| query | No | Natural language search query (e.g. 'flashinfer OOM on GB10'). Multi-word queries are tokenized and TF-IDF ranked. Pass empty string to list articles without ranking by relevance. |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The behavior matrix explicitly documents three query/sort combinations and the TF-IDF threshold (score > 0.001), going well beyond the readOnlyHint and idempotentHint annotations. It also notes determinism for a given KB snapshot, adding meaningful execution context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is compact, front-loaded with purpose, and uses a behavior matrix for efficient structured communication. Every sentence earns its place, with no redundant restatement of the schema.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given rich annotations and a detailed input schema, the description covers the core behavior variations, read-only nature, determinism, and filtering/sorting. An output schema is present, so return-value documentation is unnecessary; there are no significant gaps for an agent to select and invoke the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with detailed per-parameter descriptions, so the baseline is 3. The description adds cross-parameter semantics (e.g., query='' with any sort yields newest-first, query!='' with date_desc applies TF-IDF filtering then date sorting), which is valuable beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with 'Search the Sovereign AI Blog for articles matching a natural language query,' clearly identifying the verb, resource, and scope. It distinguishes itself from siblings like get_article and list_tags, and the behavior matrix reinforces its search/filter/sort purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description clearly establishes when to use the tool: when searching blog articles by natural language, optionally filtered by tag. It does not explicitly mention alternatives or exclusions (e.g., using get_article for a single article), so it misses a 5, but the context is otherwise unambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
get_article1 field changedInput schema / properties / slug / descriptionPrevious value: -"Article slug as returned by search_blog (e.g. 'setup-mistral-sglang-setup'). Lower-case, hyphenated."New value: +"Article slug as returned by search_blog (e.g. 'setup-llm-inference-setup'). Lower-case, hyphenated."list_tagssearch_blog10 fields changedInput schema / properties / n / maximumPrevious value: -10New value: +20Input schema / properties / query / defaultAdded value: +""Input schema / properties / query / descriptionPrevious value: -"Natural language search query (e.g. 'flashinfer OOM on GB10'). Multi-word queries are tokenized and TF-IDF ranked."New value: +"Natural language search query (e.g. 'flashinfer OOM on GB10'). Multi-word queries are tokenized and TF-IDF ranked. Pass empty string to list articles without ranking by relevance."Input schema / properties / sortAdded value: +{
+ "default": "relevance",
+ "description": "Result ordering. 'relevance' uses TF-IDF score (default for non-empty query). 'date_desc' sorts newest first (default behaviour when query is empty). When query is empty, 'relevance' is treated as 'date_desc'.",
+ "enum": [
+ "relevance",
+ "date_desc"
+ ],
+ "title": "Sort",
+ "type": "string"
+}Input schema / properties / tagAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "Optional tag filter (e.g. 'setup', 'fixes', 'strategy'). Only articles with this tag are considered. Use list_tags to discover available tags.",
+ "title": "Tag"
+}Input schema / requiredRemoved value: -[
- "query"
-]Output schema / $defs / SearchResult / properties / dateAdded value: +{
+ "default": "",
+ "description": "Publication date (ISO 8601)",
+ "title": "Date",
+ "type": "string"
+}Output schema / $defs / SearchResult / properties / quality_score / descriptionPrevious value: -"Build-time quality score, unbounded weighted composite across 13 signals from the editorial pipeline (style-aware, higher is better; thresholds depend on style)"New value: +"Build-time editorial quality score"Output schema / $defs / SearchResult / properties / quality_style / descriptionPrevious value: -"Editorial style category (e.g. 'best_practice_learnings', 'werthaltige_code_beispiele', 'conclusion', 'smart_infotainment'). Empty if not categorised."New value: +"Editorial style category"Output schema / $defs / SearchResult / properties / relevance_score / descriptionPrevious value: -"TF-IDF cosine similarity score, range 0.0 to 1.0 (higher is more relevant)"New value: +"TF-IDF cosine similarity score, 0.0 to 1.0 (1.0 = direct date-sorted hit when query is empty)"diagnose_sglangget_articlesearch_blogClaiming proves that you control a remote MCP connector. It does not move, proxy, or interrupt the server.
Open the connector listing, choose Claim ownership, and sign in to Glama.
Complete one verification method:
GitHub identity — fastest for official registry listings. For a namespace such as io.github.alice/server, link the matching GitHub user, then choose Claim with GitHub. An organization namespace such as io.github.acme/server also needs that organization to have installed the Glama AI GitHub App and approved its permissions, because GitHub discloses organization membership only to apps it has installed. Use HTTP or DNS when it has not.
HTTP challenge — works when you can deploy a public file. Generate a token, publish the exact JSON Glama shows at /.well-known/glama.json on the same origin as the connector, then choose Check HTTP challenge.
DNS challenge — works when you control DNS but cannot change the server. Generate a token, create the exact TXT record Glama shows, wait for it to propagate, then choose Check DNS challenge.
After verification, Glama sends a confirmation email and gives you access to listing details, thumbnails, health checks, and analytics. Keep the HTTP file or DNS record in place: Glama periodically checks it and ownership remains verified while the token is discoverable.
The HTTP ownership file has this structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"claim": "glama_claim_..."
}Claim tokens are opaque, stable, and bound to the signed-in Glama account. They contain no email address or other personal information. If Glama can no longer discover a verified HTTP or DNS token, it starts a seven-day grace period before removing claim-based access. Restore the same token during that period to keep ownership verified. Never publish an email address, Glama session token, GitHub token, or connector credential as ownership proof.
If verification fails, confirm that you copied the current token exactly. The HTTP file must be public, return valid JSON with a successful HTTP response, and stay on the connector's origin. DNS changes may need more time to propagate. A claim cannot transfer to a different origin or hostname: if the connector target changes, Glama starts the grace period and the new target must be claimed separately after the previous claim is released.
For a connector linked to the official MCP Registry, registry updates continue to replace its name, description, and URL by default. After claiming, open Manage connector and enable Use Glama listing details as the source of truth if edits made on Glama should be preserved. Categories and thumbnails are always managed on Glama; registry linkage and technical connection settings continue to sync.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
To improve your MCP server's ranking:
Claim ownership of the server listing
Complete the server profile with an accurate description and thumbnail
Provide a test profile so Glama can connect to and evaluate the server
Keep tool definitions clear and complete to earn a high Tool Definition Quality Score (TDQS)
Route real usage through the Glama Gateway; more recorded successful server uses also improve the ranking
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
No comments yet. Be the first to start the discussion!
Add one secure layer between your agents and this server.
Each tool targets a distinct operation: configuration validation, article retrieval, tag listing, and article search. There is no functional overlap, so an agent can easily distinguish them.
All tool names follow a consistent snake_case verb_noun pattern (e.g., diagnose_sglang, get_article, list_tags, search_blog), making them predictable and easy to remember.
Four tools is a reasonable number for a focused blog server, though the inclusion of a diagnostic tool (diagnose_sglang) slightly broadens the scope. The count still feels well-scoped and not excessive.
The blog-related tools cover reading operations (get, search, browse tags) adequately; a listing endpoint is handled via search with an empty query. The diagnostic tool is an additional feature, but there are no obvious gaps in core blog functionality.